基于抗混叠轮廓波的乳腺图像降噪与增强方法

乳腺X射线成像是乳腺疾病早期检测的有效手段.然而典型的乳腺X射线图像往往对比度低,噪声污染严重,本文提出一种新颖的基于抗混叠轮廓波变换的乳腺图像降噪及增强方案.首先分析了原始轮廓波变换的频谱混叠问题,设计出一种能稀疏表示图像边界及纹理信息,同时能抑制混叠影响的抗混叠轮廓波变换;在此基础上,分别采用高斯分布与广义拉普拉斯分布来刻划噪声相关及信号相关的变换系数,实现阈值萎缩降噪;接着对处理后的系数进行非线性增强,达到增强乳腺图像中细节信息的效果.实验结果表明,本文方法能有效提高乳腺图像的质量,在计算机辅助乳腺诊断方面有较高应用价值.

Mammography images denoising and enhancement based on aliasing-free contourlet transform

X-Ray mammography is the most effective method for the early detection of breast diseases.However,the typical digital mammography images are usually noisy and have low contrast.A novel scheme for mammography image denoising and enhancement based on aliasing-free contourlet transform is proposed.First,the aliasing problem of the original contourlet transform is analyzed,the aliasing-free contourlet transform which can represent the edges and texture of image more sparsely as well as to suppress the aliasing ...